LabCompass

Jihyung Kil

Computer Science · The Ohio State University

OpenAlex
Early career · publishing since 2017Rising activity
Multimodal Machine Learning ApplicationsTopic ModelingDomain Adaptation and Few-Shot LearningAdvanced Image and Video Retrieval TechniquesNatural Language Processing Techniques

Publications

23

Citations

91

Est. group size

~1

Recurring co-author estimate

Active years

10

Publishing since 2017

Research summary
AI-generated

Jihyung Kil works on multimodal machine learning, focusing on how AI systems combine vision and language, such as answering questions about images, understanding text embedded in scenes, navigating environments from language instructions, and generating personalized or chart-based content. Much of the work involves improving reasoning in visual question answering and grounding language models in visual or interaction data like eye-tracking and GUI screens.​ This research is relevant to students interested in vision-language models, multimodal reasoning, and applied natural language processing.

Multimodal vision-language learningVisual question answering and reasoningScene-text and document understandingVision-and-language navigationMultimodal large language model applications

Publication output was sparse before 2021 but has grown notably since, peaking in 2024 with continued activity into 2025-2026.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence
Publications per year over the last 10 years — averaging 3.6/year recently
2017: 1 publication171819202021: 4 publications212022: 3 publications222023: 1 publication232024: 8 publications8242025: 4 publications252026: 2 publications26
Recent publications
Publishes in
  • arXiv (Cornell University)×11
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)×1
  • Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing×1
  • CRI eBooks×1
  • Open MIND×1
Similar researchers
By research-topic overlap

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 19, 2026.

Claim or correct this profile